A Multicenter Evaluation of the Impact of Therapies on Deep Learning-Based Electrocardiographic Hypertrophic Cardiomyopathy Markers

Abstract

Artificial intelligence-enhanced electrocardiography (AI-ECG) can identify hypertrophic cardiomyopathy (HCM) on 12-lead ECGs and offers a novel way to monitor treatment response. Although the surgical or percutaneous reduction of the interventricular septum (SRT) represented initial HCM therapies, mavacamten offers an oral alternative. We aimed to assess the use of AI-ECG as a strategy to evaluate biologic responses to SRT and mavacamten. We applied an AI-ECG model for HCM detection to electrocardiography images from patients who underwent SRT across 3 sites: Yale New Haven Health System (YNHHS), Cleveland Clinic Foundation (CCF), and Atlantic Health System (AHS) and to electrocardiography images from patients receiving mavacamten at YNHHS. A total of 70 patients underwent SRT at YNHHS, 100 at CCF, and 145 at AHS. At YNHHS, there was no significant change in the AI-ECG HCM score before versus after SRT (before SRT: median 0.55 [interquartile range 0.24 to 0.77] vs after SRT: 0.59 [0.40 to 0.75]). The AI-ECG HCM scores also did not improve after SRT at CCF (0.61 [0.32 to 0.79] vs 0.69 [0.52 to 0.79]) and AHS (0.52 [0.35 to 0.69] vs 0.61 [0.49 to 0.70]). Of the 36 YNHHS patients on mavacamten therapy, the median AI-ECG score before starting mavacamten was 0.41 (0.22 to 0.77), which decreased significantly to 0.28 (0.11 to 0.50, p <0.001 by Wilcoxon signed-rank test) at the end of a median follow-up period of 237 days. In conclusion, we observed a lack of improvement in AI-based HCM score with SRT, in contrast to a significant decrease with mavacamten. Our approach suggests the potential role of AI-ECG for serial point-of-care monitoring of pathophysiologic improvement after medical therapy in HCM using ECG images.